© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 884
    Prev
    Next
    INDEX
    Explanations

    will be or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovenant
    2.48
    FOREIGN
    2.47
    Constit
    2.47
    이스
    2.46
    ﻓ
    2.44
    நாத
    2.39
    SourceObject
    2.34
    ﺷ
    2.30
    ﻅ
    2.29
    awaiter
    2.26
    POSITIVE LOGITS
    oughby
    3.36
    uwe
    2.67
    িখিত
    2.54
    kommen
    2.54
     "+
    2.49
    ज्ज
    2.38
    orus
    2.35
    ført
    2.32
    c
    2.32
    id
    2.27
    Activations Density 1.126%

    No Known Activations